Senior Compiler Software Development Engineer - AI/ML
Core
Design, develop, and optimize compiler transformations and operator lowerings to enable state-of-the-art AI training and inference workloads on AMD GPU platforms.
Role type
Senior IC compiler software engineer (AI/ML)
Builds
ROCm software ecosystem and ONNX Runtime execution stack
Domain
High-performance computing, AI/ML, GPU architecture
Deliverable
production ML models
Required skills
C++, MLIR, LLVM, GPU programming (HIP/CUDA/Triton), compiler optimization, performance profiling, Linux development
Preferred skills
Machine learning frameworks, model execution pipelines, graph-level optimization, kernel-level optimization, reinforcement learning
Technologies
MLIR, LLVM, ROCm, ONNX Runtime, HIP, CUDA, Triton, Git
Responsibilities
Design and optimize compiler transformations and operator lowerings; Develop scalable solutions for portability and performance across AMD GPU architectures; Implement, validate, and maintain ONNX operators and microbenchmark test suites; Lead performance optimization for AI training, fine-tuning, RL, and inference; Design and implement graph-level, kernel-level, and runtime-level optimizations; Analyze workload execution characteristics for compute efficiency and memory utilization; Drive performance characterization and benchmarking across pre-silicon and post-silicon environments.
Seniority
Senior, hands-on IC
